Compare · ModelsLive · 2 picked · head to head
GPT-4o-mini (2024-07-18) vs Qwen3 30B A3B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3 30B A3B wins on 5/5 benchmarks
Qwen3 30B A3B wins 5 of 5 shared benchmarks. Leads in arena · knowledge · math.
Category leads
arena·Qwen3 30B A3Bknowledge·Qwen3 30B A3Bmath·Qwen3 30B A3Bcoding·Qwen3 30B A3B
Hype vs Reality
Attention vs performance
GPT-4o-mini (2024-07-18)
#171 by perf·no signal
Qwen3 30B A3B
#199 by perf·#2 by attention
Best value
Qwen3 30B A3B
1.1x better value than GPT-4o-mini (2024-07-18)
GPT-4o-mini (2024-07-18)
115.2 pts/$
$0.38/M
Qwen3 30B A3B
124.8 pts/$
$0.31/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
5 benchmarks · 2 models
GPT-4o-mini (2024-07-18)Qwen3 30B A3B
Chatbot Arena Elo · Overall
Qwen3 30B A3B leads by +8.8
GPT-4o-mini (2024-07-18)
1317.7
Qwen3 30B A3B
1326.5
GPQA diamond
Qwen3 30B A3B leads by +31.9
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4o-mini (2024-07-18)
17.0
Qwen3 30B A3B
48.9
Lech Mazur Writing
Qwen3 30B A3B leads by +8.1
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
GPT-4o-mini (2024-07-18)
67.2
Qwen3 30B A3B
75.3
OTIS Mock AIME 2024-2025
Qwen3 30B A3B leads by +55.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4o-mini (2024-07-18)
6.8
Qwen3 30B A3B
62.7
WeirdML
Qwen3 30B A3B leads by +18.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-4o-mini (2024-07-18)
11.8
Qwen3 30B A3B
29.8
Full benchmark table
| Benchmark | GPT-4o-mini (2024-07-18) | Qwen3 30B A3B |
|---|---|---|
Chatbot Arena Elo · Overall | 1317.7 | 1326.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 17.0 | 48.9 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 67.2 | 75.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 6.8 | 62.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 11.8 | 29.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.15 | $0.60 | 128K tokens (~64 books) | $2.62 | |
| $0.12 | $0.50 | 131K tokens (~66 books) | $2.15 |